Contributed Talk Sessions | Poster Sessions | All Posters | Search Papers

Poster Session A: Tuesday, August 12, 1:30 – 4:30 pm, de Brug & E‑Hall

Measuring Cognitive Control in Vision-Language Models

Dezhi Luo¹, Maijunxian Wang², Bingyang Wang³, Tianwei Zhao⁴, Yijiang Li⁵, Hokin Deng⁴; ¹University of Michigan - Ann Arbor, ²University of California, Berkeley, ³Emory University, ⁴Johns Hopkins University, ⁵University of California, San Diego

Presenter: Dezhi Luo

Cognitive control refers to the ability to flexibly coordinate thought and action in pursuit of internal goals. A standard method for assessing cognitive control involves conflict tasks that contrast congruent and incongruent trials, measuring the ability to prioritize relevant information while suppressing interference. We evaluate 108 vision-language models on three classic conflict tasks and their more demanding "squared" variants across 2,220 trials. Model performance corresponds closely to human behavior under resource constraints and reveals individual differences. This results indicate that some form of human-like executive function—albeit limited—may have emerged in current multi-modal foundational models.

Topic Area: Predictive Processing & Cognitive Control

Extended Abstract: Full Text PDF